music-skill plugin
Original instrumental music written as notes, with no audio generator: the agent composes, the skill reviews and mixes.
- 182 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The agent installs a renderer and sound banks and runs synthesis scripts on the user's machine.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add plugins/music-skillDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The agent installs a renderer and sound banks and runs synthesis scripts on the user's machine.
This is third-party code. Review the repository files before installing.
What it does
The agent writes the score itself: it plans form and theme and gives each note a pitch and length. The skill reviews the score for issues such as parallel fifths and octaves, performs parts on sampled instruments through FluidSynth and synthesizers, mixes them on buses with reverb and sets loudness to a target level. The default is minus 16 LUFS, minus 14 for streaming. Output is MP3 and WAV, MIDI, a stem per part and a project file where one note can be changed and only the affected part re-rendered. No model trained on other people's recordings is involved.
Who it is for. Game and video developers whose agent already knows scene lengths and cut points and can write music to those numbers.
Good fit when
- You need a looping theme for a game level of exactly the right length.
- Music must peak on a reveal in a video and stay quieter under narration.
- You want to open the result, move one note and hear the change without rebuilding everything.
- A client needs MIDI and stems for finishing in a studio.
Not a fit when
- You need vocals: the skill writes instrumental music.
- The machine has no room for several gigabytes of sound banks.
- You want one click with no renderer and sound-bank install.
Example request
Write a one-minute looping town theme for my RPG: recorder, harp and light strings.Limitations
Before the first piece the agent installs a renderer and sound banks: about 3.7 GB of downloads and roughly five minutes on the author's test machine. Python 3.10 or newer is required. Results depend on the model: the author gives seven examples from different models and says all were shown, not the best. Samples carry licences you can check, but verify the terms of the banks you use before a commercial release. Render time grows with the number of parts: from 22 seconds for a fughetta to 108 seconds for an orchestral overture on 24 threads.
How to disable. Remove the plugin in Claude Code and delete the downloaded sound banks and renderer by hand from the directory the agent chose.
FAQ
How do I install it in Claude Code?
Run `/plugin marketplace add owoevan-dev/music-skill`, then `/plugin install music-skill@music-skill`.
How do I install it in Codex and other agents?
With `npx skills add owoevan-dev/music-skill`.
What files do I get?
MP3 and WAV, MIDI, a stem per part, the buses and reverb returns and the project file.
Why not use a music generator?
A generator hands you a finished waveform. Here the result is readable decisions: melody, voicing, drum velocity, and changing one note re-renders only the affected part.
What does the score review check?
Sustained minor seconds and ninths between parts, notes outside the written chords, parallel fifths and octaves and close intervals too low in the register.
Discussion
No questions or reviews yet.
Related
Plugins29 skills for composing and arranging pop music: from a brief the agent fills in a spec sheet for Suno, YuE2 or MIDI
A local studio plus skill: the agent writes the score and real instrument recordings play it, with no music-generation model.
A skill that turns a song recording into a five-piece school band arrangement: MIDI, PDF and an editable MuseScore file
A MiniMax skill that turns a short song description and tagged lyrics into a detailed prompt for the MiniMax Music 3 generator
A skill that makes a music video for your song: every frame is drawn by code and six steps with pauses lead from analysis to edit
17 skills for writing song lyrics: the agent answers five questions, then fills in a LYR-SPEC sheet to check the draft against.
README in short
The plugin ships for Claude Code and Codex with one `music-production` skill. The README example walks through the chain: write, review, perform, render, mix and master.
README badge
Original SKILL.md
--- name: music-production description: "Composes, arranges, performs and mixes original instrumental music as editable notes. The agent writes every note into a project file; scripts check the score, play it on sampled instruments (pianos, guitars, basses, drums, orchestra, saxophones, erhu, steel drum, mallets, organ) or built-in synthesizers, Surge XT presets and drum machines with player-like timing, dynamics, swing and legato, mix it with buses, sidechain, delays and reverbs, and master it to MIDI, stems, an MP3 and seamless game loops. No audio-generation model: every note can be changed and re-rendered. Use it whenever the user wants an original instrumental track, game, film, video or visual novel music, an RPG scene, horror or anime-opening-style cue, orchestral, baroque, piano, jazz, blues, bossa nova or organ music, pop ballads, rock, metal, EDM, techno, synthwave, chiptune, lo-fi, boom bap or trap beats, an arrangement, a revision of one phrase, editable MIDI, stems or a mix, even if they only ask for 'a song' or 'some music'." license: "MIT; scripts/surge_host.py is GPL-3.0-or-later (LICENSES/GPL-3.0-or-later.txt)" compatibility: "Python 3.10+ with NumPy. FluidSynth 2.x and FFmpeg 6 or newer: pinned portable builds on Windows x64, the system packages on Linux and macOS. Sound banks are downloaded once from this project's GitHub release (twenty-five built here, five repacked unchanged from FreePats), each checked against a pinned SHA-256, with each publisher's own download as the fallback. No GPU and no audio model." metadata: author: "owoevan-dev" version: "0.6.0" --- # Music production The music is written, not generated. You decide every note, chord, velocity and placement; the scripts validate the project, question the score, perform it, render it on sampled instruments, mix and master it, and measure the result. A clean render shows the pipeline worked, not that the music does. Listening decides that. What it does and does not do (say so when it matters to the request): - **Does**: complete instrumental pieces up to 30 minutes and 64 parts, one meter per project with a tempo map; sampled instruments, subtractive and FM synthesizers, Surge XT with its 3,008 patches (optional, installed by default), drum machines, an additive synth voice and noise transitions; player-like timing and dynamics, swing, staggered chords, legato and pitch bends; production tools (sidechain ducking, tempo-synced delay, filter sweeps, saturation, gates, tape wobble, vinyl noise); MIDI, processed stems, a mixed and mastered WAV, FLAC and MP3. - **Does not**: sing or set lyrics, host your own VST plugins (only the bundled Surge XT runs), invent articulations a sample bank does not contain, or judge musical quality from numbers. ## Workflow Copy this checklist into the project's notes and tick it off. Each step ends on its done-criterion. - [ ] **0. Setup**: `studio.py doctor --config <config>` passes. Without a configuration, tell the user what the setup installs, its size and how long it takes, and run it once they agree ([setup.md](references/setup.md)); keep the configuration where the next session will find it (the user's choice, for example `~/.music-skill/`). Install banks for the parts you plan, by group or name (`fetch_soundbanks.py --only`), not all thirty up front ([soundbanks.md](references/soundbanks.md)). - [ ] **1. Brief**: duration, mood, style, the foreground instrument and the delivery format are settled from the request; ask only for what blocks the composition. Place the piece on the style maps: one entry, or a primary entry with others borrowed for some axes, each borrowing with its reason, written into the project's `style` ([style-maps.md](references/style-maps.md)). For a game, also the use (loop, one-shot or layers), how long a player stays and where the loop starts ([game-music.md](references/game-music.md)). For an anime opening or a J-rock or J-pop band cue, the length (TV size is about 90 s) and the instrument that carries the vocal line ([anime-opening.md](references/anime-opening.md)). For a scene in a visual novel or an RPG, the cue's place in the set, whether the lines are voiced, and the engine ([scene-music.md](references/scene-music.md)). For orchestra or pipe organ, the ensemble, the room and the dynamic range ([orchestration.md](references/orchestration.md), [organ.md](references/organ.md)); for solo piano or a small ensemble, [piano-and-chamber.md](references/piano-and-chamber.md). For EDM, techno, future bass, synthwave or chiptune, the style, tempo and use ([electronic.md](references/electronic.md)); for lo-fi, boom-bap or trap beats, [beats.md](references/beats.md); for jazz, blues, bossa nova, funk or city pop, [jazz-and-funk.md](references/jazz-and-funk.md); for baroque music, [baroque.md](references/baroque.md). For film or video underscore, music timed to picture, or a suspense or horror cue, [film-score.md](references/film-score.md); for instrumental pop or a ballad, [pop-and-ballad.md](references/pop-and-ballad.md); for rock or metal, [rock-and-metal.md](references/rock-and-metal.md). A brief and a revision log exist in the project folder. - [ ] **2. Form and theme**: sections with a function each, a planned high point and an ending; a motif in real pitches and rhythm, tested against the bass and simple harmony before other parts are written: the hook first, phrases that breathe, sections built by restating it; an energy plan per section and support parts with a rhythm of their own ([arrangement.md](references/arrangement.md); the high point and the melody, [climax-and-melody.md](references/climax-and-melody.md); chords and keys, [harmony.md](references/harmony.md); variation and groove, [development-and-groove.md](references/development-and-groove.md)). - [ ] **3. Project file**: written to [schema.md](references/schema.md), usually by a composition script of your own in the project folder; `studio.py validate` passes and lists no warnings (an unknown field is a typo that does nothing). - [ ] **4. Performance**: velocities, gates and timing shaped by phrase; player-like deviation from `musiclib.expression` (`drift='time'`, so a revised note moves nothing else); legato on sustained sampled leads, bends on lead guitar ([performance-and-mix.md](references/performance-and-mix.md)). - [ ] **5. Revision rounds**: each round is one `studio.py round` into a new folder (`r1`, `r2`, ...), with `--previous` the round before. It validates the project, reviews the score with the configuration (so notes far from their samples are found), renders a draft (the same audio as a full render; `mix.chain` is `"bus"` for a finished mix), analyzes it (`--reference` where a genre reference fits, `--span` for a passage) and compares it with the previous round, printing each step's summary. Every review question has a musical decision (a prepared tension, a loop that now moves, or a fix); review also asks where nothing changes and where parts move as blocks or never push, about notes outside the written chord that are not resolved by step, parallel fifths and octaves between independent parts and close intervals under their low interval limits, and, with Surge XT installed, about built-in synth presets a Surge patch covers. Section levels, spectrum, tonal balance, stereo and lead presence are explained or fixed. The comparison shows that only the intended parts and bars changed; if anything else did, find out why first. One cause at a time, then a full-form pass; `studio.py profile` shows whether density, register, repetition and the melody's phrases follow the plan section by section. - [ ] **6. Listen**: the user heard the full piece; a round's `--clip <file>.mp3` gives them its change old then new at equal loudness (`studio.py compare --clip` does it for any two renders). - [ ] **7. Deliver**: a full render (`studio.py render`, without `--draft`) completes with every check passed. Master, FLAC, MP3, MIDI, stems (and `returns/` for a remix) and project, and for a game loop `loop.wav`/`loop.ogg` with the loop points; a credit only where a bank the user added asks for one (the banks the setup installs ask nothing of the music); measured checks; what changed and what is still open. Then `studio.py clean <project> --keep <final render> --keep <last round>` lists the piece's older renders, rounds and audition caches and the cache entries those two do not use; check the list, then run it again with `--remove`. It removes only what the tools made for that piece, by the records they wrote, never follows a link, and leaves alone a folder a render, round or audition is still working in. ## Commands `scripts/studio.py` is the entry point. Resolve its absolute path from this skill's folder; do not assume the working directory. ```text python <skill>/scripts/studio.py doctor --config <config.json> python <skill>/scripts/studio.py round <project>/song.json --config <config.json> --output <project>/r2 --previous <project>/r1 --clip <project>/r1_r2.mp3 python <skill>/scripts/studio.py render <project>/song.json --config <config.json> --output <project>/final python <skill>/scripts/studio.py clean <project> --keep <project>/final --keep <project>/r6 --remove # without --remove: the list only